Talent Tracer – AI Driven Interview Preparation Engine for Job Seekers using LLMs
Talent Tracer is an artificial intelligence- based interview preparation platform to assist job applicants in improving their technical, behavioral, and soft skills through systematic assessment. Though most candidates are able to clear aptitude and screening tests, they fail in HR and technical interviews because they lack systematic feedback and practical exposure. Talent Tracer fills this void by using AI-based tests to give detailed insights into a candidate's communication, confidence, and body language. The platform starts by comparing the candidate's resume and the job description, identifying key skills, experience, and possible gaps. From this, it creates customized interview questions on technical, behavioral, and situational issues. Candidates can answer in three modes—text, audio, or video—providing flexibility in preparation. AI-driven models subsequently score every response. Text inputs are processed by DeepSeek NLP, scoring coherence, relevance, and accuracy. Audio responses are transcribed with Whisper ASR and scored for fluency, pronunciation, tone, and confidence. Video responses are processed in real-time with CNN-based classifiers to score facial expressions, head movements, posture, and hand presence. One of the major advantages of Talent Tracer is its real-time video analysis, which analyzes body language as the candidate answers, making it possible to assess quickly and efficiently. Audio is also captured and analyzed independently to offer a detailed verbal communication review. The platform compiles all the response scores and creates a comprehensive performance report, providing personalized feedback, analysis of strengths and weaknesses, and specific improvement recommendations. Overall, Talent Tracer provides an analytics-based interview practice experience.
Authors
- V Akshaya
- R Vejaysundaram
- H Santhosh
Institutions
- Artificial Intelligence in Medicine (Canada) (CA)
Publication Details
- Published
- 2025-06-05
- DOI
- https://doi.org/10.1109/iccsp64183.2025.11088608
- Citations
- 1
- Primary Topic
- Imbalanced Data Classification Techniques
- Type
- article
- Field-Weighted Citation Impact
- 2.48